gestionabilidad_v1_batch16

This model is a fine-tuned version of dccuchile/tulio-chilean-spanish-bert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3453
• Accuracy: 0.9419
• Precision: 0.9422
• Recall: 0.9419
• F1: 0.9420

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0985	0.2670	200	0.4983	0.9118	0.9207	0.9118	0.9135
0.1098	0.5340	400	0.3588	0.9225	0.9261	0.9225	0.9234
0.1049	0.8011	600	0.2562	0.9325	0.9322	0.9325	0.9319
0.0706	1.0681	800	0.4060	0.9309	0.9330	0.9309	0.9314
0.0376	1.3351	1000	0.3807	0.9339	0.9346	0.9339	0.9341
0.0406	1.6021	1200	0.3532	0.9365	0.9367	0.9365	0.9366
0.0528	1.8692	1400	0.2903	0.9452	0.9452	0.9452	0.9452
0.0624	2.1362	1600	0.3112	0.9439	0.9442	0.9439	0.9440
0.0219	2.4032	1800	0.3662	0.9419	0.9422	0.9419	0.9420
0.021	2.6702	2000	0.3364	0.9452	0.9452	0.9452	0.9452
0.0297	2.9372	2200	0.3453	0.9419	0.9422	0.9419	0.9420

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0